This notebook contains a set of analyses for analyzing Gyges boardgamegeek collection. The bulk of the analysis is focused on building a user-specific predictive model to predict the games that the specified user is likely to own. This enables us to ask questions like, based on the games the user currently owns, what games are a good fit for their collection? What upcoming games are they likely to purchase?
## ℹ The workflow being saved contains a recipe, which is 61.13 Mb in memory. If this was not intentional, please set the control setting `save_workflow =
## ℹ FALSE`.
We can look at a basic description of the number of games that the user owns, has rated, has previously owned, etc.
What years has the user owned/rated games from? While we can’t see when a user added or removed a game from their collection, we can look at their collection by the years in which their games were published.
We can look at the most frequent types of categories, mechanics, designers, and artists that appear in a user’s collection.
We’ll examine a predictive model trained on a user’s collection for games published through 2020. How many games has the user owned/rated/played in the training set (games prior to 2020)?
username | dataset | period | games_owned | games_rated |
Gyges | training | published before 2020 | 1,063 | 1,252 |
Gyges | validation | published 2020 | 75 | 76 |
Gyges | test | published after 2020 | 60 | 46 |
The main outcome we will be modeling for the user is owned, which refers to whether the user currently owns or has a previously owned a game in their collection. Our goal is to train a predictive model to learn the probability that a user will add a game to their collection based on its observable features.
We can examine coefficients from the model we trained, which is a logistic regression with elastic net regularization (which I will refer to as a penalized logistic regression). Positive values indicate that a feature increases a user’s probability of owning/rating a game, while negative values indicate a feature decreases the probability. To be precise, the coefficients indicate the effect of a particular feature on the log-odds of a user owning a game.
Why did the model identify these features? We can make density plots of the important features for predicting whether the user owned a game. Blue indicates the density for games owned by the user, while grey indicates the density for games not owned by the user.
Binary predictors can be difficult to see with this visualization, so we can also directly examine the percentage of games in a user’s collection with a predictor vs the percentage of all games with that predictor.
% of Games with Feature | ||||
username | Feature | In_Collection | All_Games | Ratio |
Gyges | Fantasy Flight Games | 7.8% | 1.5% | 5.35 |
Gyges | Wooden Pieces Boards | 4.3% | 1.0% | 4.33 |
Gyges | Miniatures Game | 16.7% | 4.0% | 4.14 |
Gyges | Civilization | 6.9% | 1.7% | 4.12 |
Gyges | Political | 7.6% | 2.3% | 3.37 |
Gyges | Fighting | 23.9% | 7.2% | 3.33 |
Gyges | ZMan Games | 6.4% | 2.1% | 3.02 |
Gyges | Variable Player Powers | 37.6% | 12.8% | 2.94 |
Gyges | Games With Solitaire Rules | 18.0% | 6.3% | 2.85 |
Gyges | Rio Grande Games | 7.3% | 2.9% | 2.54 |
Gyges | Area Majority Influence | 21.0% | 8.3% | 2.54 |
Gyges | Iello | 4.8% | 2.0% | 2.45 |
Gyges | Science Fiction | 18.3% | 7.6% | 2.39 |
Gyges | Stronghold Games | 2.2% | 0.9% | 2.32 |
Gyges | Asmodee | 8.6% | 3.7% | 2.31 |
Gyges | Fantasy | 27.0% | 12.4% | 2.17 |
Gyges | GMT Games | 4.2% | 2.0% | 2.12 |
Gyges | Napoleonic | 1.7% | 1.0% | 1.69 |
Gyges | The Avalon Hill Game Co | 2.7% | 1.7% | 1.59 |
Gyges | Sports | 2.4% | 2.0% | 1.21 |
Gyges | Action Dexterity | 3.9% | 4.9% | 0.79 |
Gyges | Movies TV Radio Theme | 2.9% | 4.7% | 0.63 |
Gyges | Puzzle | 1.2% | 3.4% | 0.36 |
Gyges | Paper And Pencil | 0.8% | 2.7% | 0.32 |
Gyges | Artist Redmond A Simonsen | 0.0% | 1.3% | 0.00 |
Before predicting games in upcoming years, we can examine how well the model did and what games it liked in the training set. In this case, we used resampling techniques (cross validation) to ensure that the model had not seen a game before making its predictions.
An easy way to examine the performance of classification model is to view a separation plot. We plot the predicted probabilities from the model for every game (from resampling) from lowest to highest. We then overlay a blue line for any game that the user does own. A good classifier is one that is able to separate the blue (games owned by the user) from the white (games not owned by the user), with most of the blue occurring at the highest probabilities (right side of the chart).
We can display this information in table form, displaying the 100 games with the highest probability of ownership, adding a blue line when the user does own the game.
Rank | Published | ID | Name | Pr(Owned) | Owned |
1 | 1997 | 42 | Tigris & Euphrates | 0.975 | yes |
2 | 2017 | 174430 | Gloomhaven | 0.965 | yes |
3 | 2017 | 162886 | Spirit Island | 0.953 | yes |
4 | 2017 | 220308 | Gaia Project | 0.952 | no |
5 | 2010 | 54361 | Heroscape Master Set: Battle for the Underdark | 0.945 | yes |
6 | 2010 | 73171 | Earth Reborn | 0.943 | yes |
7 | 2008 | 38453 | Space Alert | 0.931 | yes |
8 | 2018 | 260428 | Pandemic: Fall of Rome | 0.920 | yes |
9 | 2011 | 96848 | Mage Knight Board Game | 0.920 | yes |
10 | 2015 | 171623 | The Voyages of Marco Polo | 0.917 | yes |
11 | 2013 | 146278 | Tash-Kalar: Arena of Legends | 0.912 | no |
12 | 2000 | 475 | Taj Mahal | 0.906 | yes |
13 | 2012 | 120677 | Terra Mystica | 0.905 | yes |
14 | 2018 | 244711 | Newton | 0.904 | no |
15 | 2006 | 25417 | BattleLore | 0.894 | yes |
16 | 1979 | 121 | Dune | 0.887 | yes |
17 | 2019 | 169427 | Middara: Unintentional Malum – Act 1 | 0.876 | yes |
18 | 2017 | 233078 | Twilight Imperium: Fourth Edition | 0.873 | no |
19 | 2011 | 66356 | Dungeons & Dragons: Wrath of Ashardalon Board Game | 0.873 | yes |
20 | 2005 | 13642 | Louis XIV | 0.868 | yes |
21 | 2015 | 175155 | Forbidden Stars | 0.866 | yes |
22 | 2014 | 164153 | Star Wars: Imperial Assault | 0.863 | yes |
23 | 2017 | 234671 | Pandemic: Rising Tide | 0.863 | no |
24 | 1998 | 3 | Samurai | 0.862 | yes |
25 | 2010 | 62227 | Labyrinth: The War on Terror, 2001 – ? | 0.861 | yes |
26 | 2012 | 104162 | Descent: Journeys in the Dark (Second Edition) | 0.857 | yes |
27 | 2017 | 193728 | Pendragon: The Fall of Roman Britain | 0.851 | no |
28 | 2016 | 131111 | Codex: Card-Time Strategy – Deluxe Set | 0.851 | yes |
29 | 2019 | 269385 | The Lord of the Rings: Journeys in Middle-Earth | 0.850 | no |
30 | 2018 | 313010 | Cosmic Encounter: 42nd Anniversary Edition | 0.850 | no |
31 | 2016 | 215437 | Codex: Card-Time Strategy – Core Set | 0.850 | no |
32 | 2016 | 167791 | Terraforming Mars | 0.850 | no |
33 | 2004 | 11170 | Heroscape Master Set: Rise of the Valkyrie | 0.849 | yes |
34 | 2019 | 253574 | Crusader Kings | 0.845 | no |
35 | 2002 | 3284 | Star Wars: Epic Duels | 0.845 | yes |
36 | 2019 | 281946 | Aftermath | 0.844 | no |
37 | 2007 | 27976 | Heroscape Master Set: Swarm of the Marro | 0.843 | yes |
38 | 2004 | 9446 | Blue Moon | 0.840 | yes |
39 | 2009 | 45315 | Dungeon Lords | 0.839 | yes |
40 | 2011 | 42776 | Gears of War: The Board Game | 0.838 | yes |
41 | 2008 | 38707 | Bushido: Der Weg des Kriegers | 0.834 | yes |
42 | 2015 | 179460 | Stronghold: 2nd edition | 0.833 | no |
43 | 2012 | 121921 | Robinson Crusoe: Adventures on the Cursed Island | 0.832 | yes |
44 | 2017 | 221107 | Pandemic Legacy: Season 2 | 0.831 | yes |
45 | 2013 | 133528 | City of Remnants | 0.829 | yes |
46 | 2011 | 72125 | Eclipse | 0.825 | yes |
47 | 2016 | 205637 | Arkham Horror: The Card Game | 0.824 | yes |
48 | 2004 | 10908 | Minotaur Lords | 0.822 | yes |
49 | 2017 | 157979 | Tau Ceti: Planetary Crisis | 0.820 | no |
50 | 2019 | 285984 | Last Bastion | 0.817 | yes |
51 | 2014 | 159675 | Fields of Arle | 0.817 | no |
52 | 2016 | 215436 | Codex: Card-Time Strategy – Starter Set | 0.816 | no |
53 | 2016 | 169786 | Scythe | 0.816 | yes |
54 | 2018 | 167355 | Nemesis | 0.814 | no |
55 | 2018 | 205896 | Rising Sun | 0.814 | yes |
56 | 2004 | 9216 | Goa | 0.813 | yes |
57 | 2004 | 9609 | War of the Ring | 0.805 | no |
58 | 2010 | 25292 | Merchants & Marauders | 0.803 | no |
59 | 2016 | 152172 | Nova Aetas | 0.800 | no |
60 | 2007 | 28143 | Race for the Galaxy | 0.795 | yes |
61 | 2016 | 179275 | One Deck Dungeon | 0.790 | yes |
62 | 1995 | 112 | Condottiere | 0.789 | no |
63 | 2015 | 169255 | A Game of Thrones: The Card Game (Second Edition) | 0.785 | no |
64 | 2012 | 104363 | Rex: Final Days of an Empire | 0.783 | yes |
65 | 1995 | 46 | Medici | 0.781 | no |
66 | 2005 | 12493 | Twilight Imperium: Third Edition | 0.779 | yes |
67 | 2016 | 198928 | Pandemic: Iberia | 0.776 | yes |
68 | 2000 | 939 | Star Wars: The Queen's Gambit | 0.775 | yes |
69 | 2014 | 154203 | Imperial Settlers | 0.772 | yes |
70 | 2017 | 170771 | Sword & Sorcery | 0.772 | yes |
71 | 2011 | 102548 | Dungeon Fighter | 0.771 | yes |
72 | 2013 | 146439 | BattleLore: Second Edition | 0.769 | yes |
73 | 2006 | 21882 | Blue Moon City | 0.766 | yes |
74 | 2013 | 144239 | Impulse | 0.764 | yes |
75 | 2015 | 182028 | Through the Ages: A New Story of Civilization | 0.763 | yes |
76 | 2006 | 21241 | Neuroshima Hex! 3.0 | 0.760 | yes |
77 | 2019 | 266507 | Clank!: Legacy – Acquisitions Incorporated | 0.758 | no |
78 | 2002 | 4098 | Age of Steam | 0.753 | yes |
79 | 1997 | 105 | Colossal Arena | 0.753 | yes |
80 | 2018 | 207729 | The Edge: Dawnfall | 0.752 | no |
81 | 2000 | 883 | Ivanhoe | 0.751 | no |
82 | 2018 | 170604 | Renegade | 0.751 | no |
83 | 2011 | 99392 | Colonial: Europe's Empires Overseas | 0.749 | no |
84 | 2019 | 239942 | Black Rose Wars | 0.748 | yes |
85 | 2019 | 264220 | Tainted Grail: The Fall of Avalon | 0.747 | yes |
86 | 2011 | 50768 | Ninjato | 0.747 | no |
87 | 2018 | 154910 | Darklight: Memento Mori | 0.746 | no |
88 | 2008 | 37111 | Battlestar Galactica: The Board Game | 0.746 | no |
89 | 2000 | 823 | The Lord of the Rings | 0.745 | yes |
90 | 2014 | 119788 | Hyperborea | 0.741 | yes |
91 | 2012 | 104710 | Wiz-War (Eighth Edition) | 0.738 | yes |
92 | 2015 | 163175 | Yashima: Legend of the Kami Masters | 0.738 | yes |
93 | 2017 | 226501 | Dragonfire | 0.735 | no |
94 | 2009 | 42124 | Dungeon Twister 2: Prison | 0.734 | yes |
95 | 2019 | 270971 | Era: Medieval Age | 0.733 | yes |
96 | 2010 | 70512 | Luna | 0.732 | no |
97 | 2019 | 251247 | Barrage | 0.732 | yes |
98 | 2011 | 83330 | Mansions of Madness | 0.730 | no |
99 | 2015 | 170216 | Blood Rage | 0.730 | yes |
100 | 2018 | 238412 | Heropath: Dragon Roar | 0.729 | no |
We can also more formally assess how well the model did in resampling by looking at the area under the receiver operating characteristic. A perfect model would receive a score of 1, while a model that cannot predict the outcome will default to a score of 0.5. The extent to which something is a good score depends on the setting, but generally anything in the .8 to .9 range is very good while the .7 to .8 range is perfectly acceptable.
Another way to think about the model performance is to view its lift, or its ability to detect the positive outcomes over that of a null model. High lift indicates the model can much more quickly find all of the positive outcomes (in this case, games owned or played by the user), while a model with no lift is no better than random guessing. A gains chart is another way to view this.
Finally, we can understand the performance of the model by examining its calibration. If the model assigns a probability of 5%, how often does the outcome actually occur? A well calibrated model is one in which the predicted probabilities reflect the probabilities we would observe in the actual data. We can assess the calibration of a model by grouping its predictions into bins and assessing how often we observe the outcome versus how often our model expects to observe the outcome.
A model that is well calibrated will closely follow the dashed line - its expected probabilities match that of the observed probabilities. A model that consistently underestimates the probability of the event will be over this dashed line, be a while a model that overestimates the probability will be under the dashed line.
What games does the model think Gyges is most likely to own that are not in their collection?
Published | ID | Name | Pr(Owned) | Owned |
2017 | 220308 | Gaia Project | 0.952 | no |
2013 | 146278 | Tash-Kalar: Arena of Legends | 0.912 | no |
2018 | 244711 | Newton | 0.904 | no |
2017 | 233078 | Twilight Imperium: Fourth Edition | 0.873 | no |
2017 | 234671 | Pandemic: Rising Tide | 0.863 | no |
What games does the model think Gyges is least likely to own that are in their collection?
Published | ID | Name | Pr(Owned) | Owned |
2018 | 228740 | Kitten Klash | 0.008 | yes |
2010 | 67486 | Bubble Talk | 0.011 | yes |
2012 | 134637 | Channel A | 0.011 | yes |
2009 | 40800 | Miss Poutine | 0.012 | yes |
2017 | 219513 | Bärenpark | 0.012 | yes |
Top 25 games most likely to be owned by the user in each year, highlighting in blue the games that the user has owned.
rank | 2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 | 2019 |
1 | Terra Mystica | Tash-Kalar: Arena of Legends | Star Wars: Imperial Assault | The Voyages of Marco Polo | Codex: Card-Time Strategy – Deluxe Set | Gloomhaven | Pandemic: Fall of Rome | Middara: Unintentional Malum – Act 1 |
2 | Descent: Journeys in the Dark (Second Edition) | City of Remnants | Fields of Arle | Forbidden Stars | Codex: Card-Time Strategy – Core Set | Spirit Island | Newton | The Lord of the Rings: Journeys in Middle-Earth |
3 | Robinson Crusoe: Adventures on the Cursed Island | BattleLore: Second Edition | Imperial Settlers | Stronghold: 2nd edition | Terraforming Mars | Gaia Project | Cosmic Encounter: 42nd Anniversary Edition | Crusader Kings |
4 | Rex: Final Days of an Empire | Impulse | Hyperborea | A Game of Thrones: The Card Game (Second Edition) | Arkham Horror: The Card Game | Twilight Imperium: Fourth Edition | Nemesis | Aftermath |
5 | Wiz-War (Eighth Edition) | Patchistory | Roll for the Galaxy | Through the Ages: A New Story of Civilization | Codex: Card-Time Strategy – Starter Set | Pandemic: Rising Tide | Rising Sun | Last Bastion |
6 | Pax Porfiriana | A Study in Emerald | La Granja | Yashima: Legend of the Kami Masters | Scythe | Pendragon: The Fall of Roman Britain | The Edge: Dawnfall | Clank!: Legacy – Acquisitions Incorporated |
7 | The Great Zimbabwe | BattleCON: Devastation of Indines | Istanbul | Blood Rage | Nova Aetas | Pandemic Legacy: Season 2 | Renegade | Black Rose Wars |
8 | Tzolk'in: The Mayan Calendar | Glass Road | Fire in the Lake | Mombasa | One Deck Dungeon | Tau Ceti: Planetary Crisis | Darklight: Memento Mori | Tainted Grail: The Fall of Avalon |
9 | Il Vecchio | Dark Darker Darkest | Dogs of War | Magic: The Gathering – Arena of the Planeswalkers | Pandemic: Iberia | Sword & Sorcery | Heropath: Dragon Roar | Era: Medieval Age |
10 | Exodus: Proxima Centauri | Dungeon Command: Blood of Gruumsh | Yomi (Second Edition) | Kingdom Death: Monster | Star Trek: Frontiers | Dragonfire | Neon Gods | Barrage |
11 | Archipelago | Dungeon Twister: The Card Game | Galaxy Defenders | 504 | Star Wars: Rebellion | One Deck Dungeon: Forest of Shadows | New Frontiers | Cthulhu: Death May Die |
12 | Mice and Mystics | Lewis & Clark: The Expedition | Temporum | Super Dungeon Explore: Forgotten King | Mansions of Madness: Second Edition | Here I Stand: 500th Anniversary Edition | Underwater Cities | Dune |
13 | Android: Netrunner | Gearworld: The Borderlands | Age of War | Zombicide: Black Plague | Aeon's End | Fallout | Dungeon Alliance | Unmatched: Robin Hood vs. Bigfoot |
14 | Android: Infiltration | Level 7 [Omega Protocol] | Shadows of Brimstone: City of the Ancients | Metal Adventures | New Angeles | Too Many Bones | Lords of Hellas | Pax Pamir: Second Edition |
15 | Dungeon Command: Curse of Undeath | Legacy: The Testament of Duke de Crecy | Arcadia Quest | Drakon (Fourth Edition) | Dust 1947 | First Martians: Adventures on the Red Planet | Donning the Purple | Red Alert: Space Fleet Warfare |
16 | Virgin Queen | Prosperity | Pixel Tactics 3 | Space Cadets: Away Missions | The Others | Dark Souls: The Board Game | Shadows of Brimstone: Forbidden Fortress | Bios: Origins (Second Edition) |
17 | 1989: Dawn of Freedom | Zpocalypse | Yomi: Round 1 | Pandemic Legacy: Season 1 | Conan | Aristeia! | Tsukuyumi: Full Moon Down | Unmatched Game System |
18 | Space Cadets | Cuba Libre | Akrotiri | Dungeons & Dragons: Temple of Elemental Evil Board Game | Falling Sky: The Gallic Revolt Against Caesar | Legend of the Five Rings: The Card Game | Heroes of Land, Air & Sea | Machina Arcana (Second/Third Edition) |
19 | Lyssan | Burning Suns | Deus | Risk: Star Wars Edition | DOOM: The Board Game | This War of Mine: The Board Game | Star Wars: X-Wing (Second Edition) | Tiny Towns |
20 | Dungeon Command: Tyranny of Goblins | BioShock Infinite: The Siege of Columbia | DungeonQuest Revised Edition | Warhammer Quest: The Adventure Card Game | A Feast for Odin | Immortals | Deep Madness | Aeon's End: Legacy |
21 | Puzzle Strike Shadows | Forbidden Desert | Alchemists | Runebound (Third Edition) | SeaFall | Zpocalypse 2: Defend the Burbs | Too Many Bones: Undertow | Marvel Champions: The Card Game |
22 | Zombicide | Rococo | Legendary Encounters: An Alien Deck Building Game | Pixel Tactics 5 | Perdition's Mouth: Abyssal Rift | Lisboa | Yellow & Yangtze | Gandhi: The Decolonization of British India, 1917 – 1947 |
23 | Andean Abyss | Eldritch Horror | Spells of Doom | Heat | Dead of Winter: The Long Night | Mythic Battles: Pantheon | Zombicide: Green Horde | Black Angel |
24 | Neuroshima: Convoy | Pixel Tactics 2 | The Lord of the Ice Garden | BattleCON: Fate of Indines | Magic: The Gathering – Arena of the Planeswalkers: Shadows over Innistrad | Pericles: The Peloponnesian Wars | Heroes of Terrinoth | Rurik: Dawn of Kiev |
25 | Kemet | Hegemonic | Thunderstone Advance: Worlds Collide | Pax Pamir | Virus | Runewars Miniatures Game | Root | The Hunters A.D. 2114 |
Interactive table for predictions from resampling.
We’ll validate the model by looking at its predictions for games published in 2020. That is, how well did a model trained on a user’s collection through 2020 perform in predicting games for the user in 2020?
username | outcome | dataset | method | .metric | .estimate |
Gyges | owned | validation | glmnet | roc_auc | 0.764 |
Table of top 50 games from 2020, highlighting games that the user owns.
Published | ID | Name | Pr(Owned) | Owned |
2020 | 291457 | Gloomhaven: Jaws of the Lion | 0.893 | yes |
2020 | 314040 | Pandemic Legacy: Season 0 | 0.840 | no |
2020 | 281655 | High Frontier 4 All | 0.684 | yes |
2020 | 318472 | Blood Bowl: Second Season Edition | 0.672 | no |
2020 | 273703 | Altar Quest | 0.657 | yes |
2020 | 280794 | Etherfields | 0.650 | no |
2020 | 294484 | Unmatched: Cobble & Fog | 0.618 | yes |
2020 | 256999 | Project: ELITE | 0.595 | yes |
2020 | 325635 | Unmatched: Little Red Riding Hood vs. Beowulf | 0.594 | no |
2020 | 184267 | On Mars | 0.592 | no |
2020 | 259061 | Skytear | 0.553 | yes |
2020 | 317985 | Beyond the Sun | 0.546 | yes |
2020 | 177014 | Giga-Robo! | 0.541 | no |
2020 | 253506 | Versailles 1919 | 0.532 | yes |
2020 | 271055 | Dwellings of Eldervale | 0.523 | no |
2020 | 287325 | Exceed: Shovel Knight – Hope Box | 0.510 | no |
2020 | 322985 | Shadows of Brimstone: Swamps of Death (Revised Edition) | 0.502 | no |
2020 | 245224 | La Belle Époque | 0.486 | no |
2020 | 248125 | Monumental | 0.477 | yes |
2020 | 174400 | BattleCON: Wanderers of Indines | 0.470 | yes |
2020 | 326767 | Infinity N4: Core Rules | 0.470 | no |
2020 | 299317 | Aeon's End: Outcasts | 0.465 | no |
2020 | 207486 | Infinities: Defiance of Fate | 0.463 | no |
2020 | 316377 | 7 Wonders (Second Edition) | 0.456 | no |
2020 | 298572 | Cosmic Encounter Duel | 0.454 | yes |
2020 | 301919 | Pandemic: Hot Zone – North America | 0.435 | no |
2020 | 246900 | Eclipse: Second Dawn for the Galaxy | 0.432 | yes |
2020 | 249275 | The Silver River | 0.431 | no |
2020 | 256940 | Krosmaster: Blast | 0.428 | no |
2020 | 233673 | Exploration | 0.421 | no |
2020 | 315060 | Unmatched: Buffy the Vampire Slayer | 0.418 | no |
2020 | 282922 | Windward | 0.415 | no |
2020 | 295604 | Rangers of Shadow Deep: Deluxe Edition | 0.411 | no |
2020 | 316554 | Dune: Imperium | 0.404 | no |
2020 | 287326 | Exceed: Shovel Knight – Shadow Box | 0.400 | no |
2020 | 256964 | Dark Rituals: Malleus Maleficarum | 0.375 | no |
2020 | 286021 | Free Market: NYC | 0.370 | no |
2020 | 284639 | Gatefall | 0.369 | yes |
2020 | 206480 | Imperial Struggle | 0.366 | yes |
2020 | 309630 | Small World of Warcraft | 0.364 | no |
2020 | 272533 | Kingdom Rush: Rift in Time | 0.361 | yes |
2020 | 284777 | Unmatched: Jurassic Park – InGen vs Raptors | 0.357 | no |
2020 | 257193 | Starcadia Quest | 0.355 | yes |
2020 | 242994 | Onimaru | 0.354 | no |
2020 | 322984 | Shadows of Brimstone: City of the Ancients (Revised Edition) | 0.352 | no |
2020 | 315196 | Dungeons & Dragons: Adventure Begins | 0.339 | no |
2020 | 304434 | Victim: The Cursed Forest | 0.339 | no |
2020 | 285972 | HEXplore It: The Sands of Shurax | 0.334 | no |
2020 | 306481 | Tawantinsuyu: The Inca Empire | 0.325 | no |
2020 | 285853 | Infinity Defiance | 0.324 | no |
We can then refit our model to the training and validation set in order to predict all upcoming games for the user.
Examine the top 50 games for upcoming games, highlighting in blue ones the user already.
Published | ID | Name | Pr(Owned) | Owned |
2022 | 295770 | Frosthaven | 0.868 | no |
2022 | 331106 | The Witcher: Old World | 0.801 | no |
2021 | 262201 | Sword & Sorcery: Ancient Chronicles | 0.796 | no |
2022 | 317321 | Darkest Dungeon: The Board Game | 0.735 | no |
2022 | 254127 | Europa Universalis: The Price of Power | 0.711 | no |
2021 | 260524 | Beyond Humanity: Colonies | 0.699 | no |
2021 | 332420 | Nexum: Galaxy | 0.690 | no |
2022 | 322524 | Bardsung | 0.684 | no |
2021 | 333539 | The Siege of Runedar | 0.683 | no |
2022 | 273814 | Deliverance | 0.664 | no |
2021 | 333144 | Stronghold: Undead (Second Edition) | 0.662 | no |
2022 | 299106 | Fractal: Beyond the Void | 0.651 | no |
2021 | 322708 | Descent: Legends of the Dark | 0.637 | yes |
2022 | 251661 | Oathsworn: Into the Deepwood | 0.636 | no |
2021 | 291572 | Oath: Chronicles of Empire and Exile | 0.619 | yes |
2021 | 260934 | Ignite | 0.618 | no |
2022 | 266018 | Trinidad | 0.614 | no |
2022 | 282775 | The Warp | 0.613 | no |
2022 | 335764 | Unmatched: Battle of Legends, Volume Two | 0.593 | no |
2021 | 298383 | Golem | 0.584 | no |
2022 | 331398 | Mythic Battles: Ragnarök | 0.569 | no |
2021 | 318560 | Witchstone | 0.566 | no |
2021 | 336794 | Galaxy Trucker | 0.561 | yes |
2021 | 259066 | Commands & Colors: Samurai Battles | 0.550 | yes |
2022 | 275802 | Carnival Zombie: 2nd Edition | 0.544 | no |
2021 | 273330 | Bloodborne: The Board Game | 0.536 | yes |
2021 | 330608 | Cryo | 0.529 | yes |
2021 | 295785 | Euthia: Torment of Resurrection | 0.525 | no |
2022 | 350079 | Puzzle Strike 2 | 0.524 | no |
2021 | 332075 | Warhammer Quest: Cursed City | 0.520 | no |
2021 | 336195 | League of Dungeoneers | 0.516 | no |
2021 | 331212 | Aeon's End: Legacy of Gravehold | 0.506 | no |
2021 | 277080 | Titans | 0.497 | no |
2022 | 252315 | The Everrain | 0.496 | no |
2021 | 310100 | Nemesis: Lockdown | 0.487 | no |
2021 | 266448 | Imperium: The Contention | 0.487 | yes |
2021 | 285967 | Ankh: Gods of Egypt | 0.477 | yes |
2021 | 291828 | Car Wars (Sixth Edition) | 0.469 | no |
2022 | 303731 | Primal: The Awakening | 0.469 | no |
2021 | 302413 | Steamwatchers | 0.460 | no |
2021 | 280984 | Ruins: Death Binder | 0.459 | no |
2022 | 317511 | Tindaya | 0.458 | no |
2022 | 281647 | Stellaris: Infinite Legacy | 0.457 | no |
2021 | 283387 | Rocketmen | 0.450 | no |
2022 | 242705 | Aeon Trespass: Odyssey | 0.450 | no |
2022 | 330950 | Age of Galaxy | 0.445 | no |
2021 | 318184 | Imperium: Classics | 0.442 | yes |
2021 | 329450 | Equinox | 0.440 | no |
2021 | 306202 | Philosophia: Floating World | 0.439 | no |
2021 | 295147 | Good Puppers | 0.437 | yes |